تقرير
TAP: The Attention Patch for Cross-Modal Knowledge Transfer from Unlabeled Modality
العنوان: | TAP: The Attention Patch for Cross-Modal Knowledge Transfer from Unlabeled Modality |
---|---|
المؤلفون: | Wang, Yinsong, Shahrampour, Shahin |
سنة النشر: | 2023 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Statistics - Machine Learning |
الوصف: | This paper addresses a cross-modal learning framework, where the objective is to enhance the performance of supervised learning in the primary modality using an unlabeled, unpaired secondary modality. Taking a probabilistic approach for missing information estimation, we show that the extra information contained in the secondary modality can be estimated via Nadaraya-Watson (NW) kernel regression, which can further be expressed as a kernelized cross-attention module (under linear transformation). This expression lays the foundation for introducing The Attention Patch (TAP), a simple neural network add-on that can be trained to allow data-level knowledge transfer from the unlabeled modality. We provide extensive numerical simulations using real-world datasets to show that TAP can provide statistically significant improvement in generalization across different domains and different neural network architectures, making use of seemingly unusable unlabeled cross-modal data. Comment: Accepted to TMLR |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2302.02224 |
رقم الأكسشن: | edsarx.2302.02224 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |